Categories › AI & Agents › Multi-agent, orchestration & workflows
Materials simulations for AI agents over MCP: binding token quote before every run, record after it.
Remote server: your requests and data go to api.materialscodegraph.com. Claude Code: claude mcp add --transport http materialscodegraph https://api.materialscodegraph.com/mcp · Claude app: Settings → Connectors → Add custom connector.
The tools this server listed when we connected to it, in its own words.
mcg_catalog — Enabled simulation kinds (each with example mcg_quote arguments that price, a note naming what must exist first, or both; traced says whethemcg_rates — The public rate card: token_usd, overheads, rate_card_version. FREE, no arguments; also a connectivity check.mcg_quote — Price a simulation. FREE: no hardware starts. Returns quote_id, quote_hash, tokens, rate_card_version, wall_s, expires_at, resource_class, rmcg_clusters — Connected clusters: id, name, preset (hive or auto), status (pending until the agent's first sync; connected; stale: the agent stopped syncimcg_stage — Create a DRAFT simulation whose input files are uploaded before pricing. FREE. Takes the same kind, spec, study, material and conditions as mcg_run — Launch the quoted simulation. SPENDS TOKENS: provisions hardware and bills the account. Requires the quote_id and quote_hash from mcg_quote mcg_list_runs — List runs, newest first: every run of this key's owner, or one quote's runs when quote_id is given. Returns at most limit rows (default 20, mcg_get_study — Fetch a study (the project a quote's `study` named) with its member simulations and their latest runs. Pass study_id or the exact name. Retumcg_study_members — Add simulations to a study and remove them from it. You must own the study (get its id from mcg_get_study) and every listed simulation; a mimcg_list_studies — Your projects and their subprojects. A project is a study with no parent; a subproject is a study filed under one project. Each entry carriemcg_update_study — Describe and file a study you own. name renames it; summary sets its one-line purpose; story_md replaces its long narrative. parent_id filesmcg_delete_study — Delete a study you own: the study and its membership list go. Its simulations, runs, artifacts and spend are untouched and stay reachable bymcg_archive — Archive or unarchive a simulation you own. Archiving hides it from the app's lists and studies; its runs, artifacts and spend are untouched,mcg_get_run — Fetch a run's state, event timeline and LLM spend. The payload leads with a derived summary (state, current_stage, billing {quoted_tokens, cmcg_cancel_run — Cancel a run from any non-terminal state before collecting (a collecting run's outputs are delivered and charged: 409). The cancel request imcg_fetch_artifacts — List a run's collected artifacts as a typed manifest: artifacts, a list of path, bytes, stage and sha256 per file, plus removed on a file thmcg_get_artifact — Fetch one artifact file's TEXT content, up to max_bytes (default 65536), with an explicit truncation note. Binary content REJECTS with unsupNot tested by KitScout yet. When our harness runs it, pros, cons and the tasks we tried appear here, with the date and evidence.